Great piece. The prescriptions (held-back tests, charter above memory, generational handoff) all work one agent at a time. I'm curious how you'd apply them to the case in section 4, where no single agent fails its own tests but the system drifts through its handoffs.
K-ion14 built governance that operates between agents at runtime, because, as you point out, once the summary exists the influence is already baked in.
Retiring an agent on a schedule is a management-system question before it is an engineering one. ISO/IEC 42001:2023, published 18 December 2023, sets requirements for an AI management system organised around Plan-Do-Check-Act, which puts the check step after deployment rather than at release. For a ten-person firm with no AI team, that turns into one cheap habit: a fixed date in the calendar to re-run the original task set against whatever is in production, and a named owner for the decision to reset the memory store. Neither needs new tooling, and both survive the person who set them up.
My agent rarely forgets. I spent 6 months training and refining its understanding. All training is stored in its repository. It checks the repository to refresh instructions every time. Is it perfect. Maybe one day it forgets an instruction then the next time it doesn’t. But the errors are really small and not cumulative
Great piece. The prescriptions (held-back tests, charter above memory, generational handoff) all work one agent at a time. I'm curious how you'd apply them to the case in section 4, where no single agent fails its own tests but the system drifts through its handoffs.
K-ion14 built governance that operates between agents at runtime, because, as you point out, once the summary exists the influence is already baked in.
Retiring an agent on a schedule is a management-system question before it is an engineering one. ISO/IEC 42001:2023, published 18 December 2023, sets requirements for an AI management system organised around Plan-Do-Check-Act, which puts the check step after deployment rather than at release. For a ten-person firm with no AI team, that turns into one cheap habit: a fixed date in the calendar to re-run the original task set against whatever is in production, and a named owner for the decision to reset the memory store. Neither needs new tooling, and both survive the person who set them up.
My agent rarely forgets. I spent 6 months training and refining its understanding. All training is stored in its repository. It checks the repository to refresh instructions every time. Is it perfect. Maybe one day it forgets an instruction then the next time it doesn’t. But the errors are really small and not cumulative